Brief bio
I am interested in probabilistic approaches to deep learning - especially deep generative models of sequential data and machine learning applied in health technology and climate applications. Currently, I primarily research how to model extreme weather events by introducing modelling components that draws upon stochastic dynamical systems. Previously, my research has focused on how we can make audio models that generalize to real-world use scenarios. I've been working on variational autoencoders and how probabilistic modelling enables us to, e.g., learn robust latent representations, incorporate prior knowledge, and utilize uncertainty quantification. Below is a collection of some recent work and news.

Recent Work and News

UC Berkeley/ICSI Postdoc

I started as a postdoc at UC Berkeley BAIR and ICSI with A. Krishnapriyan and M. Mahoney. I'll continue my work on neural stochastic differential equations focusing on modelling extreme weather events using heavy-tailed diffusions.

UC Berkeley/ICSI stay during PhD: Continuously deep hierarchical VAE

I visited Berkeley working with M. Mahoney. We developed continuously deep hierarchical variational autoencoders by combining neural stochstic differential equations with hierarchical variational autoencoder models.

Directional archetypal analysis

Multi-subject, multi-modal modelling of functional neuroimaging data using directional statistics. Published in Frontiers in Neuroscience (paper, Twitter thread).


The Variational Inference Time-domain Audio Separation Network (VI-TasNet) is probabilistic extension of TasNets. The work shows how we can incorporate domain-knowledge priors in modelling and quantify separation performance uncertainty unintrusively. We also investigate how speaker separation generalization can be understood through the lense of rate-distortion analysis.

(preprint available)

Research Pitch Battle winner

I won Danish Sound Days research pitch battle competition, see their post on the competition above.

Client adaptation in federated learning

We present a federated learning approach for learning a client adaptable, robust model when data is non-identically and non-independently distributed (non-IID) across clients, as well as a way to simulate non-IID clients.

(arXiv, presented at FL-ICML 2020 )

Deep unsupervised learning course

I organized and helped teach a course on deep unsupervised learning at DTU, modelled on the Berkeley CS294-158.

(course page)

Interactive machine learning demos

I developed a series of machine learning demos for an introductory machine learning course at DTU .

Danish Foreign Ministry's World Image Grant//Visiting biomedical engineer in Nepal

We received a grant of 7k EUR for the production of a documentary for an alternative view on a developing country. Through Engineering World Health at DTU I was deployed at Okhaldhunga Community Hospitals. My work at the hospital entailed hospital equipment repair, healthcare staff training (proper use and maintenance), and needfinding (initial phase design research and planning). Photo by S. Sundgaaard.